readygpu

NVIDIA GeForce RTX 4060 Ti 16GB vs AMD Radeon RX 7900 XT

For running models locally, priced in Germany. At 8k context the first runs 41 models fully in memory, the second 49.

In short

The AMD Radeon RX 7900 XT has more memory for models: 20 GB against 16 GB. At 8k context the AMD Radeon RX 7900 XT runs 49 of the models we track fully in memory and the NVIDIA GeForce RTX 4060 Ti 16GB 41; only the AMD Radeon RX 7900 XT holds Qwen 3.8 27B. On the models both run fully in memory, the AMD Radeon RX 7900 XT is about 2.5× as fast as the NVIDIA GeForce RTX 4060 Ti 16GB (estimated, median across models). In Germany the NVIDIA GeForce RTX 4060 Ti 16GB costs 839 € at eBay (used) and the AMD Radeon RX 7900 XT 877 € at eBay (used): the NVIDIA GeForce RTX 4060 Ti 16GB is 38 € cheaper.

Updated . Speeds are estimates; how they are worked out.

NVIDIA GeForce RTX 4060 Ti 16GB

839 €

eBay, used (asking)

Add to build
AMD Radeon RX 7900 XT

877 €

eBay, used (asking)

Add to build

Specifications

SpecNVIDIA GeForce RTX 4060 Ti 16GBAMD Radeon RX 7900 XT
GPUGeForce RTX 4060 Ti 16GBRadeon RX 7900 XT
Memory16 GB GDDR620 GB GDDR6
Memory bus128-bit320-bit
Memory bandwidth288 GB/s800 GB/s
FP16 compute44 TFLOPS103 TFLOPS
SoftwareCUDAROCm
Board power165 W315 W
PCIe generationGen 4Gen 4
PCIe lanesx8x16

What each runs

Estimated decode speed with the most precise quant that fits each one est.

ModelNVIDIA GeForce RTX 4060 Ti 16GBAMD Radeon RX 7900 XT
Qwen 3.8 27Boffload24tok/sQ4_K_M
Qwen 3.6 27Boffload25tok/sQ4_K_M
Qwen 3.5 27Boffload25tok/sQ4_K_M
Gemma 4 26B-A4Boffload78tok/sQ5_K_M
Devstral Small 2 24B11tok/sQ4_K_M24tok/sQ5_K_M
GLM 4.7 Flashoffload76tok/sQ4_K_M
gpt-oss 20B41tok/sMXFP4100tok/sMXFP4
Qwen3 Coder 30B-A3Boffload100tok/sQ4_K_M
Gemma 4 12B14tok/sQ8_034tok/sQ8_0
Qwen 3.5 9B18tok/sQ8_045tok/sQ8_0
Mistral Small 3.2 24B11tok/sQ4_K_M24tok/sQ5_K_M
Gemma 3 27Boffload25tok/sQ4_K_M
Qwen3 14B13tok/sQ6_K26tok/sQ8_0
Ministral 3 14B11tok/sQ8_028tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B18tok/sQ8_044tok/sQ8_0
Qwen3 8B18tok/sQ8_044tok/sQ8_0
Phi-4 14B13tok/sQ6_K26tok/sQ8_0
Qwen 3.5 4B37tok/sQ8_092tok/sQ8_0
Ministral 3 8B18tok/sQ8_043tok/sQ8_0
Granite 4.2 8B17tok/sQ8_041tok/sQ8_0
Gemma 4 E4B21tok/sQ8_052tok/sQ8_0
LFM2.5 8B-A1B73tok/sQ8_0180tok/sQ8_0
Llama 3.1 8B23tok/sQ6_K57tok/sQ6_K
Qwen2.5 0.5B283tok/sQ8_0697tok/sQ8_0
Qwen3.5 0.8B192tok/sQ8_0472tok/sQ8_0
Qwen3.5 2B115tok/sQ5_K_M283tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B84tok/sQ8_0207tok/sQ8_0
MiniCPM5 2B59tok/sQ8_0145tok/sQ8_0
LFM2.5 2.6B53tok/sQ8_0130tok/sQ8_0
LFM2.5 VL 3B53tok/sQ8_0130tok/sQ8_0
Spark X2.5 4B53tok/smlx-4bit130tok/smlx-4bit
Kimi VL A3B Thinking 250649tok/sQ4_K_M79tok/sQ8_0
granite vision 4.1 4b42tok/sQ8_0103tok/sQ8_0
granite 4.2 3b39tok/sQ8_096tok/sQ8_0
Kimi VL A3B39tok/smlx-6bit75tok/smlx-8bit
Mellum2.1 12B A2.5B Thinking38tok/sQ8_094tok/sQ8_0
FrogNano 4B 260936tok/sQ8_089tok/sQ8_0
DeepSeek R1 Distill Qwen 7B21tok/sQ8_051tok/sQ8_0
GLM 4 9B 041421tok/smlx-5bit51tok/smlx-5bit
DeepSeek R1 Distill Llama 8B19tok/sQ8_046tok/sQ8_0
Ministral 3 8B Reasoning 251218tok/sQ8_043tok/sQ8_0
GLM 4.6V Flash17tok/sQ8_043tok/sQ8_0
GLM 4.1V 9B Thinking15tok/smlx-8bit36tok/smlx-8bit
DeepSeek R1 Distill Qwen 14B13tok/sQ6_K25tok/sQ8_0
Devstral Small 250711tok/sQ4_K_M24tok/sQ5_K_M
Magistral Small 250611tok/sQ4_K_M24tok/sQ5_K_M
Magistral Small 250711tok/sQ4_K_M24tok/sQ5_K_M
Magistral Small 250911tok/sQ4_K_M24tok/sQ5_K_M
LFM2.5 24B A2Boffload119tok/sQ5_K_M
Qwen 3.5 122B-A10Boffloadoffload
Gemma 4 31Boffloadoffload
Mistral Small 4 119Boffloadoffload
Qwen 3.6 35B-A3Boffloadoffload
GLM 4.5 Airwon't runoffload
Qwen 3.5 35B-A3Boffloadoffload
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 32Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
Llama 3.3 70Bwon't runoffload
granite 4.2 30boffloadoffload
Qwen3.8 27B OBLITERATEDoffloadoffload
DeepSeek R1 Distill Llama 70Bwon't runoffload
DeepSeek V4 Flashwon't runwon't run
GLM 5.3 Flashwon't runwon't run
Qwen 3.8 Flash Nextwon't runwon't run
MiniMax M2.7won't runwon't run
Nemotron 3 Super 120B-A12Bwon't runwon't run
Qwen3 Coder Nextwon't runwon't run
gpt-oss 120Bwon't runwon't run
Qwen3 Next 80B-A3Bwon't runwon't run
DeepSeek R1won't runwon't run
DeepSeek R1 0528won't runwon't run
DeepSeek R1 Zerowon't runwon't run
DeepSeek V3 0324won't runwon't run
DeepSeek V3.1won't runwon't run
DeepSeek V3.1 Terminuswon't runwon't run
DeepSeek V3.2won't runwon't run
DeepSeek V4 Flash 0731won't runwon't run
DeepSeek V4 Flash Vision Expwon't runwon't run
Devstral 2 123B Instruct 2512won't runwon't run
GLM 4.5won't runwon't run
GLM 4.5Vwon't runwon't run
GLM 4.6won't runwon't run
GLM 4.6Vwon't runwon't run
GLM 4.7won't runwon't run
GLM 5won't runwon't run
GLM 5.1won't runwon't run
GLM 5.2won't runwon't run
GLM 5.3won't runwon't run
Kimi Dev 72Bwon't runwon't run
Kimi K2won't runwon't run
Kimi K2 Instruct 0905won't runwon't run
Kimi K2 Thinkingwon't runwon't run
Kimi K2.5won't runwon't run
MiniMax M2won't runwon't run
MiniMax M2.1won't runwon't run
MiniMax M2.5won't runwon't run
MiniMax M3won't runwon't run
Mistral Medium 3.5 128Bwon't runwon't run

Questions

Which is better for local AI, the NVIDIA GeForce RTX 4060 Ti 16GB or the AMD Radeon RX 7900 XT?
Choose the AMD Radeon RX 7900 XT to run bigger models. Choose the AMD Radeon RX 7900 XT for speed. Choose the NVIDIA GeForce RTX 4060 Ti 16GB to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 4060 Ti 16GB or the AMD Radeon RX 7900 XT?
At 8k context the AMD Radeon RX 7900 XT runs 49 of the models we track fully in memory and the NVIDIA GeForce RTX 4060 Ti 16GB 41; only the AMD Radeon RX 7900 XT holds Qwen 3.8 27B.
Which is faster for local AI, the NVIDIA GeForce RTX 4060 Ti 16GB or the AMD Radeon RX 7900 XT?
On the models both run fully in memory, the AMD Radeon RX 7900 XT is about 2.5× as fast as the NVIDIA GeForce RTX 4060 Ti 16GB (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 4060 Ti 16GB and the AMD Radeon RX 7900 XT?
In Germany the NVIDIA GeForce RTX 4060 Ti 16GB costs 839 € at eBay (used) and the AMD Radeon RX 7900 XT 877 € at eBay (used): the NVIDIA GeForce RTX 4060 Ti 16GB is 38 € cheaper.

More comparisons